Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare a non-read-only, open-world, non-destructive write, so the description's job is to add flow context — and it does: the call returns a payment link, the user must open and pay it manually, and the letter is only dispatched after payment completes. That deferred-fulfillment dependency is essential behavior an agent could not infer from annotations alone. It stops short of disclosing actual price, delivery time, or what happens if payment never occurs.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Four short sentences, front-loaded with what the tool does and immediately followed by the payment prerequisite, which is the most decision-relevant fact. No filler or repeated information; only the closing confirmation rule feels slightly appended rather than integrated.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 5-parameter mutation with no output schema and one undocumented enum, the description covers the essential contract: what is created, what is returned, and that fulfillment is payment-gated. It also documents the return artifact in lieu of an output schema. Missing details (cost, delivery timeline, letterType semantics) are secondary but non-trivial for a paid physical-mail tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is only 40%, and the description compensates only partially: it stresses confirming the recipient address, which maps to the nested address object. It says nothing about letterType values ('almindelig' vs 'rekommanderet'), what fields sender must carry, or how text is rendered, leaving the enum and both address objects to be inferred from the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Opretter et fysisk tekstbrev i Danmark') plus the concrete return value ('returnerer et betalingslink'), which is more than a restatement of the name. It implicitly separates itself from the send_letter sibling by describing a deferred, payment-gated flow, but it never names that sibling, so the differentiation is behavioral rather than explicit.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

'Kræver ingen API-nøgle' hints at an alternative path and 'Bekræft altid modtagerens adresse og prisen med brugeren først' gives a hard precondition, which is useful. However, it never says when to choose this over send_letter or get_pricing, and the user-confirmation rule is an operational instruction rather than when-to-use guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.